Multi-core Research Articles

An excellent super-polarization-independent optical directional coupler based on dual-core photonic crystal fibre with a bandwidth of 390 nm

Abstract In this work, a novel structure of dual-core photonic crystal fibre (PCF) is proposed to realize the super-polarization-independent optical directional coupler, based on the feasibility of optical fibre manufacturing process and the need of practical application into account. The introduced fluorine-doped elliptical cores with a rotation angle of 45 degrees successfully realize the super-polarization-independent coupling performance within the effective wavelength range of 1230-1620nm, with a difference in coupling ratios between two polarized lights of less than 0.004%. In other words, it counteracts the negative effects of the introduction of dual cores on the structure's symmetry. This greatly reduces the difference in coupling ratio between the two polarization states and effectively eliminates the polarization-dependence of the dual-core PCF. In addition, when compared to traditional elliptical air holes, the solid elliptical structure offers greater ease of control, making manufacturing less challenging. Consequently, this innovative structure is poised for widespread adoption in today's optical communication networks.

SpyderZ: An Efficient Support Vector Machine Library for Photometric Redshift Estimation and Redshift Probability Information

We present SpyderZ, a Python-based library for photometric redshift estimation using support vector machines (implemented with scikit-learn). Our approach discretizes redshift values into uniformly-sized bins and uses one-vs-one support vector classifiers with voting strategies to produce effective probability density functions (ePDFs) over redshift for each galaxy. These ePDFs, which are not constrained to be Gaussian or any other shape, allow for our model's predictions to be used quantitatively with uncertainty analysis methods, and have been shown to enable reliable catastrophic outlier detection. Adapted from the previous IDL package SpiderZ, SpyderZ offers training and evaluation speed optimizations on the order of 102, along with support for parallelization across CPU cores. Our library also offers in-built data sanity checks, result visualizations, metric calculations, cross validation, batch evaluations, and parallelized hyperparameter search (grid search and random search).

GrainGNN: A dynamic graph neural network for predicting 3D grain microstructure

We propose GrainGNN, a surrogate model for the evolution of polycrystalline grain structure under rapid solidification conditions in metal additive manufacturing. High fidelity simulations of solidification microstructures are typically performed using multicomponent partial differential equations (PDEs) with moving interfaces. The inherent randomness of the PDE initial conditions (grain seeds) necessitates ensemble simulations to predict microstructure statistics, e.g., grain size, aspect ratio, and crystallographic orientation. Currently such ensemble simulations are prohibitively expensive and surrogates are necessary.In GrainGNN, we use a dynamic graph to represent interface motion and topological changes due to grain coarsening. We use a reduced representation of the microstructure using hand-crafted features; we combine pattern finding and altering graph algorithms with two neural networks, a classifier (for topological changes) and a regressor (for interface motion). Both networks have an encoder-decoder architecture; the encoder has a multi-layer transformer long-short-term-memory architecture; the decoder is a single layer perceptron.We evaluate GrainGNN by comparing it to high-fidelity phase field simulations for in-distribution and out-of-distribution grain configurations for solidification under laser power bed fusion conditions. GrainGNN results in 80%–90% pointwise accuracy; and nearly identical distributions of scalar quantities of interest (QoI) between phase field and GrainGNN simulations compared using Kolmogorov-Smirnov test. GrainGNN's inference speedup (PyTorch on single x86 CPU) over a high-fidelity phase field simulation (CUDA on a single NVIDIA A100 GPU) is 150×–2000× for 100-initial grain problem. Further, using GrainGNN, we model the formation of 11,600 grains in 220 seconds on a single CPU core.

CPU and GPU oriented optimizations for LiDAR data processing

Digital Terrain Models (DTM) can be accurately obtained from clouds of LiDAR points but the corresponding cloud processing time can be prohibitive. This paper describes several optimization techniques that have been applied to the Overlap Window Method (OWM) that is a key component in DTM applications. OWM was originally implemented in R which translates into serious limitations in terms of the size of the LiDAR point cloud that can be processed. We have ported the code to C++, significantly optimized the data structure to minimize memory accesses, and developed parallel implementations for CPU and GPU commodity devices using oneAPI libraries and tools. This results in CPU and GPU versions that are up to 19x and 83x faster, respectively, than an OpenMP baseline that uses eight CPU cores. Most importantly, the proposed optimizations for CPU and GPU can be paramount to get the most out of other LiDAR-based algorithms in which the careful selection of the right data structure, parallelization strategies and memory access reduction techniques will certainly result in significant performance improvements.

Development of dual-core spun yarn using different fiber as a core by hamel twisting (elasto twist) technique and its impact on the denim fabric performance

Textile industries constantly explore innovative methods to increase fabric and yarn properties meeting multiple consumer demands and yarns (dual core) especially those incorporating an elastic core have obtained concentration for their potential in producing fabrics with improved stretch and recovery properties. This study focuses on the manufacturing of yarns (double core) using Hamel Twisting (Elasto twist) techniques utilizing core materials wrapped with 'S' and 'Z' directions such as polytrimethylene terephthalate/polyethylene terephthalate (T400®), PBT (Polybutylene terephthalate), PES (Polyester) and elastane (Lycra®). The yarns are manufactured utilizing an adjusted spinning technique (ring) and the work focuses on core materials wrapped with 'S' and 'Z' direction to the dual-core spun yarns using the Hamel Twisting (Elasto twist) method and also includes the manufacturing of denim fabrics (3/1 ‘Z’ twill) utilizing the developed yarn as weft. The article presents a comprehensive analysis of yarn properties, including unevenness, strength, neps (+200), elongation, thick place (+50), hairiness, and thin place (−50), and subsequently evaluates the fabric properties, such as weight (dry and washed), elasticity %, tensile strength, growth %, tearing strength, stiffness, and shrinkage. The statistical analysis utilizes Two-way ANOVA to examine the significant variations in fabric and yarn characteristics among several core components and their wrapped directions. The findings present an understanding of the performance of yarns (double core) manufactured through the elasto twist method, offering precious insights for applications in multiple textile products, including denim fabrics.

Parallel Algorithm on Multicore Processor and Graphics Processing Unit for the Optimization of Electric Vehicle Recharge Scheduling

Parallel Algorithm on Multicore Processor and Graphics Processing Unit for the Optimization of Electric Vehicle Recharge Scheduling

EPO‐R: An efficient garbage collection scheme for long‐term transactions

SummaryThis article proposes EPO‐R, which is an efficient garbage collection scheme designed for multi‐version concurrency control (MVCC) protocols. MVCC generates a version for each update operation, and it can exhaust physical memory for dynamically changing environments such as IoT payments. Eager pruning of obsolete versions (EPO) is a novel garbage collection technique for long‐term transactions. We found room for improvement in EPO, which triggers reclamation invocation. EPO is triggered for each write operation, and it wastes CPU resources. The proposed method EPO‐R is triggered on a read operation to address this issue. The result of experiments with 64 CPU cores and workloads with the combination of short‐term and long‐term transactions demonstrated that EPO‐R exhibited 6.3 times higher throughput than that of EPO. The reason for this can be explained by analyzing the number of unreclaimable versions.

A hybrid CPU‐GPU paradigm to accelerate reactive CFD simulations

AbstractThe solution of reactive computational fluid dynamics (CFD) simulations is accelerated by the implementation of a hybrid central processing unit/graphics processing units (CPU/GPU) Finite Volume solver based on the operator‐splitting strategy, where the chemistry integration is treated independently of the flow solution. The integration of ordinary differential equations (ODEs) describing the finite‐rate chemical kinetics is solved by an adaptive multi‐block explicit solver on GPUs, while the load of the fluid solution is distributed on a multicore CPU algorithm. The resulting speed‐up for reactive CFD simulations is up to 10; the performance gain increases with the size of the mechanism. The proposed implementation is general and can be applied to any CFD problem where the governing equations for the fluid transport are coupled with an ODE system. Code validation is performed against reference solutions on a selection of test cases involving reacting flows.

QUIC on the fast lane: Extending performance evaluations on high-rate links

QUIC is a new protocol standardized in 2021 designed to improve on the widely used TCP/TLS stack. The main goal is to speed up web traffic via HTTP, but it is also used in other areas like tunneling. Based on UDP, it offers features like reliable in-order delivery, flow and congestion control, stream-based multiplexing, and always-on encryption using TLS 1.3.Unlike TCP, QUIC integrates these capabilities in user space, relying on kernel interaction solely for UDP. Operating in user space allows more flexibility but sacrifices some kernel-level efficiency and optimization that TCP benefits from. Various QUIC implementations exist, each distinct in programming language, architecture, and design.QUIC is already widely deployed on the Internet and has been evaluated, focussing on low latency, interoperability, and standard compliance. However, benchmarks on high-speed network links are still scarce.This paper presents an extension to the QUIC Interop Runner, a framework for testing the interoperability of QUIC implementations. Our contribution enables reproducible QUIC benchmarks on dedicated hardware and high-speed links. We provide results on 10G links, including multiple implementations, evaluate how OS features like buffer sizes and NIC offloading impact QUIC performance, and show which data rates can be achieved with QUIC compared to TCP. Moreover, we analyze different CPUs and CPU architectures influence reproducible and comparable performance measurements. Furthermore, our framework can be applied to evaluate the effects of future improvements to the protocol or the OS.Our results show that QUIC performance varies widely between client and server implementations from around 50Mbit/s to over 6000Mbit/s. We show that the OS generally sets the default buffer size too small. Based on our findings, the buffer size should be increased by at least an order of magnitude. Our profiling analysis identifies Packet I/O as the most expensive task for QUIC implementations. Furthermore, QUIC benefits less from AES NI hardware acceleration while both features improve the goodput of TCP to around 8000Mbit/s. The lack of support for NIC offloading from QUIC implementations results in missed opportunities for performance improvement.The assessment of CPUs from different vendors and generations revealed significant performance variations. We employed core pinning to examine if the performance of QUIC implementations is affected by the allocation to specific CPU cores. The results indicated an increased goodput of up to 20% when running on a specifically chosen core compared to a randomly assigned core. This outcome highlights the impact of CPU core selection on the performance of QUIC implementations but also for reproducible measurements.

Method for scalable and performant GPU-accelerated simulation of multiphase compressible flow

Multiphase compressible flows are often characterized by a broad range of space and time scales, entailing large grids and small time steps. Simulations of these flows on CPU-based clusters can thus take several wall-clock days. Offloading the compute kernels to GPUs appears attractive but is memory-bound for many finite-volume and -difference methods, damping speedups. Even when realized, GPU-based kernels lead to more intrusive communication and I/O times owing to lower computation costs. We present a strategy for GPU acceleration of multiphase compressible flow solvers that addresses these challenges and obtains large speedups at scale. We use OpenACC for directive-based offloading of all compute kernels while maintaining low-level control when needed. An established Fortran preprocessor and metaprogramming tool, Fypp, enables otherwise hidden compile-time optimizations. This strategy exposes compile-time optimizations and high memory reuse while retaining readable, maintainable, and compact code. Remote direct memory access realized via CUDA-aware MPI and GPUDirect reduces halo-exchange communication time. We implement this approach in the open-source solver MFC [1]. Metaprogramming results in an 8-times speedup of the most expensive kernels compared to a statically compiled program, reaching 46% of peak FLOPs on modern NVIDIA GPUs and high arithmetic intensity (about 10 FLOPs/byte). In representative simulations, a single NVIDIA A100 GPU is 7-times faster compared to an Intel Xeon Cascade Lake (6248) CPU die, or about 300-times faster compared to a single such CPU core. At the same time, near-ideal (97%) weak scaling is observed for at least 13824 GPUs on OLCF Summit. A strong scaling efficiency of 84% is retained for an 8-times increase in GPU count. Collective I/O, implemented via MPI3, helps ensure the negligible contribution of data transfers (<1% of the wall time for a typical, large simulation). Large many-GPU simulations of compressible (solid-)liquid-gas flows demonstrate the practical utility of this strategy.

Mixed-Input Residual Network for Air Temperature Forecasting by Low-Power Embedded Devices

Accuracy and model compactness are essential requirements for weather forecasting models designed for operation on low-power embedded devices. This study developed Mixed-Input Residual Network (MIRNet), a compact temperature-forecasting deep neural network model. MIRNet integrates stacked bidirectional long short-term memory layers using concatenated 1-dimensional and 2-dimensional convolutional layers to improve model accuracy. MIRNet was trained and tested on two datasets: one, IfeData, comprising historical weather data from Ile-Ife, Nigeria and the other a standard weather forecasting dataset called the Jena dataset. Training was carried out using 100 epochs of data partitioned in the standard 80:20 ratio, with an adaptable learning rate strategy. The model was tested for Nth-hour-ahead prediction for 1N24; where N are natural numbers, and performance quantified using metrics such as mean absolute percentage error (MAPE) and mean square error (MSE). The model was also implemented on a Raspberry Pi 4 device with a 1.8 GHz 64-bit quad-core ARM Cortex-A72 processor. The model achieved a MSE of 1.00 x 10-3 on the IfeData dataset, and 1.23x10-4 on the Jena dataset for 1-hour ahead forecasting. This is currently the best verifiable result achieved on the Jena dataset by any prediction model globally. For Nth hour ahead forecasting, MIRNet achieved an MSE generally below 2.0x10-3 for all values of N on the standard Jena dataset. The MSE of MIRNet for N-sequential 1-hour ahead and single Nth hour predictions using the Jena dataset reveal quadratic and linear relationships with N respectively. The model compares favourably with existing models for multi-hour predictions. The developed model is compact and has good forecasting properties.

How Does the Spatial Structure of Urban Agglomerations Affect the Spatiotemporal Evolution of Population Aging?

China has fully become an aging society, and the scientific response to population aging has become a major task that the country must face in the future. Research on population aging in the Chengdu-Chongqing urban agglomeration (CCUA) can provide a scientific basis for future population management in the CCUA. This paper applies spatial autocorrelation, geodetection, and other methods to analyze the temporal and spatial pattern of population aging and its driving factors in the CCUA from 2000 to 2020, taking districts (counties) as the basic unit and combining them with the spatial structure of the urban agglomeration. The results show that: ① in the time dimension, the population aging in CCUA has gone through the evolution process of “mild–moderate–heavy”; in the spatial dimension, the influence of the urban agglomeration’s development planning axes on the spatial differentiation of the aging population has become more and more prominent. ② The aging level has a strong spatial correlation, and with time, the spatial correlation has changed from weak to strong, and the spatial difference has increased. The dual core city shows a typical spatial pattern of a decreasing aging level in the core area and an increasing aging level in the peripheral area, and the heavily aging area is spreading along the axis. ③ The overall aging speed is high, and the aging speeds of the core cities and node cities are lower than those of other regions. There is a clearer positive correlation between the aging level and the speed of aging, showing the characteristic of “the older the faster”. ④ Endogenous factors such as the aging level and fertility level at the beginning of the period have a significant determining power on the change in the aging level, while exogenous factors such as the in-migration rate and the out-migration rate have a persistent determining power on the urban agglomerations and key areas (core cities, central cities, main axes of development, city belts, and dense urban areas).

Spatiotemporal Evolution and Causal Analysis of Rural Tourism Popularity in Jilin Province Based on Multiple Data

The digital age provides greater possibilities for quantitative research on rural tourism. This article examines Jilin Province as a case and analyzes the interannual, monthly, and holiday characteristics of rural tourism heat using big data. Using A-level rural tourism operating units as research samples, a mathematical model is constructed to evaluate the rural tourism heat from 2016 to 2021. Through a trend surface analysis and kernel density analysis, the spatiotemporal differentiation characteristics are explored; additionally, the spatial evolution law of the rural tourism hot and cold pattern is analyzed using counties as units. The research results show the following: (1) As an important component of the Jilin tourism industry, temporally, rural tourism has an overall trend of increasing popularity, with clear seasonal and holiday distribution patterns. Simultaneously, the periodic sporadic occurrence of the COVID-19 epidemic caused an obvious vulnerability in rural tourism fever. (2) Spatially, the structure of rural tourism shows an evolutionary process of “single core → multi core” and a diffusion trend of “central → eastern” and “central → western”. (3) Regarding the influencing factors, transportation conditions and resource endowments are dominant, and the impact of the economic development level is gradually weakening, while the impact of the ecological environment and industrial foundation is gradually increasing.

Vibration assessment of dual core sandwich beam with a biomimetic lamellar honeycomb core and MWCNT reinforced facesheets

The usage of sandwich structures has been increasing in the field of defense, transportation, and aerospace applications due to the many advantages like, thickness to mass ratio, high bending stiffness, and strength. In this present work, the vibration assessment of the dual-core sandwich beam with biomimetic core and multiwalled carbon nanotube (MWCNT) reinforced composite face layers has been performed. The lamellar honeycomb (LHC) core is a biomimetic design developed here from the pistachio shell structure and manufactured by 3D printing process. The mechanical characteristics of biomimetic core are measured using an alternative dynamic technique and impulse excitation test was used to assess the material properties of MWCNT composite laminates. Using finite element software, a numerical model is created for a composite dual-core sandwich beam containing MWCNTs and a biomimetic core. The developed numerical model is validated with experimental and available literature results in terms of natural frequencies and it shows good agreements. Additionally, parametric studies are performed to investigate the natural frequencies of MWCNT composite dual-core sandwich beam with biomimetic cores for ply orientation angles, aspect ratio, and support conditions. The MWCNT reinforcement in the facesheets and LHC core enhances the structural performance and stiffness of the laminated composite dual-core sandwich beam. This research will provide the valuable insights to engineers and scientists for the construction of large capacity ships and race boat structures.

Ion-molecule collision cross-section calculations using trajectory parallelization in distributed systems

Ion Mobility coupled with Mass Spectrometry (IM-MS) stands as a strong analytical method for structurally characterizing complex molecules. In IM-MS, the sample under investigation is ionized and propelled by an electric field into a drift tube, which collides against a buffer gas. The separation of the ion gas phase is then measured through the differences in their rotationally averaged Collision Cross-Section (CCS) values. The effectiveness of the measured Collision Cross-Section (CCS) for structural characterization critically depends on the validation against theoretical calculations. This validation process relies on intensive molecular mechanics simulations, which can be computationally demanding, especially for large systems such as molecular assemblies and viruses. Therefore, reliable and fast CCS calculations are needed to help interpret IM-MS experimental data. This work presents the MassCCS software, which considerably increases the CCS simulation performance by implementing a linked-cell-based algorithm, incorporating High-Performance Computing (HPC) techniques. We performed extensive tests regarding the system size, shape, and number of CPU cores. Experimental results reveal speedups up to 3 orders of magnitude faster than Collision Simulator for Ion Mobility Spectrometry (CoSIMS) and High-Performance Collision Cross Section (HPCCS), optimized solutions for CCS simulations, for a single node execution. In addition, we extended MassCCS at the inter-node level by employing OpenMP Cluster (OMPC). OMPC is an innovative programming model designed for the development of HPC applications. It streamlines the development process and simplifies software maintenance using only OpenMP directives. Notably, OMPC delivers a performance level comparable to a pure MPI implementation. This enhancement enabled expensive CCS calculations using nitrogen buffer gas for large systems such as human adenovirus with ∼11 million atoms in just ∼4 min, making MassCCS the most performant software nowadays, to the best of our knowledge. MassCCS is available as free software for Academic use at https://github.com/cces-cepid/massccs.

Efficient topology reconfiguration for NoC-based multiprocessors: A greedy-memetic algorithm

In multi-core processor systems, the Network-on-Chip (NoC) serves as a vital communication infrastructure. To ensure chip reliability during potential failures, this paper proposes a two-level topology reconfiguration algorithm with core-level redundancy technology. Initially, a heuristic topology reconfiguration method utilizing a greedy strategy is proposed to perform local replacement of faulty processing elements (PEs) and generate an initial logical topology with shorter interconnection paths between PEs. Then, an intelligent optimization method based on memetic algorithm is introduced to optimize the generated initial topology for better communication performance. The experimental results demonstrate that compared to the current state-of-the-art algorithm, the proposed algorithm achieves an average improvement of 13.92% and 30.83% on various size topologies in terms of distance factor (DF) and congestion factor (CF), which represent communication delay and traffic balance respectively. The proposed algorithm significantly enhances the communication performance of the target topology, mitigating communication latency and potential congestion problems.

Accelerating the shooting and bouncing ray based electromagnetic scattering calculations via CPU and GPU Implementations: Application to PREDICS tool

In this paper, we present the parallel computation of physical electromagnetic (EM) solvers, namely physical optics (PO), shooting and bouncing rays (SBR), and the physical theory of diffraction (PTD), which are used for EM scattering/diffraction calculations. The accelerated solvers have been tested on CPU and GPU kernels for significantly faster calculation times. As an application, the developed implementation is employed to recently developed tool of PREDICS that uses combined techniques PO, SBR, and PTD for the calculation of EM scattering/diffraction and radar cross section (RCS) from electrically large, complex objects. First, the CPU parallelization of these three combined techniques on the PREDICS code is explained. The parallelization implementation is specially tailored for the nature of SBR technique such that the CPU iteration loop is accomplished over triangular facets of the CAD file by employing a read/write spin lock task dispatching technique. Next, a lock-free implementation of the PO, SBR, and PTD techniques on the GPU threads is presented. Thanks to availability of many GPU cores, the parallelization procedure is widened such that triangular facets, observation angles of elevation and azimuth are used for a much faster calculation set-up. Numerical examples for the EM/RCS calculation of simple canonical and electrically big, complex objects are shared to demonstrate the effectiveness, accuracy and the computational acceleration based on the multi-CPU and multi-GPU implementations. The key metric of the contribution of the study is the speed-up value of the implementations. The acceleration gained via multi-CPU realization yielded directly in parallel with the number of available CPU cores. On the other hand, the acceleration factor can reach to hundreds when multi-GPUs are used. In fact, the acceleration factor has reached to 4.7 for a machine with 4 Core 8 Thread CPU processor, and 141.3 for a 2560 CUDA GPU Core system.

Energy efficiency and performance analysis of a legacy atomic scale materials modeling simulator (VASP)

AbstractThis work tackles the performance and energy consumption analysis of a legacy scientific application, the VASP (Vienna Ab-initio Simulation Package), an application commonly used by physicists and chemists for modeling materials at the atomic scale. Many of these scientific applications have been implemented in Fortran, where energy metrics instrumentation is not straightforward. We obtained performance figures (execution time and energy consumption) by instrumenting the source code using EML. This energy measurement library has been modified to introduce Fortran interfaces for these metrics. The analysis was carried out using different matrix algebra libraries, parallelization techniques, and hardware platforms, emphasizing on the MPI, OpenMP, and CUDA parallel implementations of the algorithms used in VASP. We employ various material specifications (atomic structures) and molecular sizes of a silicon-based crystal to create a set of benchmarks for these specifications, leading to some recommendations for final users regarding performance improvements. The proposed benchmarking technique assists the user in selecting the right combination of problem size, compilers, and parallelization options available in VASP. For a given system platform, the user will be able to determine not only the architecture to use (GPU or multicore processors), but also the appropriate library and parallelization according to the atomic structure and molecular size.

Analytical Gradient Using Cluster-in-Molecule RI-MP2 Method for the Geometry Optimizations of Large Systems.

We present an efficient analytical energy gradient algorithm for the cluster-in-molecule resolution-of-identity second-order Møller-Plesset perturbation (CIM-RI-MP2) method based on the Lagrange multiplier method. Our algorithm independently constructs the Lagrangian formalism within each cluster, avoiding the solution of the coupled-perturbed Hartree-Fock (CPHF) equation for the whole system. Due to this feature, the computational cost of the CIM-RI-MP2 gradients is much lower than that of other local MP2 algorithms. Benchmark calculations of several molecules containing up to 312 atoms demonstrate the general applicability of our CIM-RI-MP2 gradient algorithm. The optimized structure of a 244-atom molecule using the CIM-RI-MP2 method with the cc-pVDZ basis set is in good agreement with the corresponding crystal structure. A single-point gradient calculation conducted for a molecular cage containing 972 atoms and 9612 basis functions takes 48 h on 25 nodes, utilizing a total of 600 CPU cores. The present CIM-RI-MP2 gradient program is applicable for obtaining the optimized geometries of large systems with hundreds of atoms.

A Parallel Mining Algorithm for Maximum Erasable Itemset Based on Multi-core Processor

A Parallel Mining Algorithm for Maximum Erasable Itemset Based on Multi-core Processor